Detections
Analytics

Chainguard: vllm-openai-cuda-13.0: security update to 0.31.0-r0

medium Tenable Cloud Security Plugin ID 476112

Description

There are packages installed that are affected by a vulnerability referenced in the following CVE:

 - vLLM is an inference and serving engine for large language models. From 0.24.0 until 0.30.0, the
 Qwen2VLVideoBackend and Qwen3VLVideoBackend classes accept request-level values for the
 media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields without enforcing server-side
 ceilings. An unauthenticated caller can submit these values to the /tokenize endpoint, causing the sampler
 to decode every frame selected from attacker-controlled video input, consume disproportionate frontend
 memory, and potentially terminate the API process before scheduling or admission control. The Rust
 frontend is not affected because it rejects the media_io_kwargs field. This issue is fixed in version
 0.30.0. (CVE-2026-105758)

Solution

Update the vllm-openai-cuda-13.0 library and its related packages to version 0.31.0-r0 or later.

Plugin Details

Severity: Medium

ID: 476112

Version: Revision 1.1

Type: Local

Published: 10/17/2026

Updated: 10/17/2026

Risk Information

VPR

Risk Factor: Low

Score: 1.2

Percentile: 0.01

CVSS v2

Risk Factor: Medium

Base Score: 5

Temporal Score: 3.7

Vector: CVSS2#AV:N/AC:L/Au:N/C:N/I:N/A:P

CVSS Score Source: CVE-2026-105758

CVSS v3

Risk Factor: Medium

Base Score: 5.3

Temporal Score: 4.6

Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L

Temporal Vector: CVSS:3.0/E:U/RL:O/RC:C

Vulnerability Information

Exploit Ease: No known exploits are available

Vulnerability Publication Date: 10/5/2026

Reference Information

CVE: CVE-2026-105758